cs.LGJan 30, 2026

The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer

Authors: Yupeng Chen, Junchi Yu, Aoxi Liu, Baoyuan Wu, Philip Torr, Adel Bibi

Organizations: Torr Vision Group, University of Oxford · The Chinese University of Hong Kong, Shenzhen

Abstract

Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment. However, whether such alignment inadvertently facilitates the transfer of safety vulnerabilities across modalities remains underexplored. This question is critical as text-based jailbreak attacks are considerably more mature than audio-based ones; if they transfer systematically, current audio safety evaluations may underestimate risks originating from the text modality. In this paper, we introduce the Alignment Curse, a formally characterized and empirically validated principle showing that stronger modality alignment enables more effective transfer of attacks from text to audio, revealing a fundamental tension between capability and safety. Motivated by this principle, we conduct a comprehensive black-box evaluation of three attack categories on recent omni-models (e.g., Qwen2.5-Omni, Qwen3-Omni): text attacks, text-transferred audio attacks, and audio attacks. We find that text-transferred audio attacks perform comparably to, and often better than, audio-based attacks, exhibiting a clear advantage under audio-only access. This suggests that text-based vulnerabilities play a pivotal role in shaping audio safety risks. Finally, we empirically analyze the relationship between modality alignment and transfer effectiveness across attack methods and models, observing consistent support for the Alignment Curse: tighter modality alignment leads to more effective cross-modality attack transfer.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs

    Apr 17, 2026Jaechul Roh, Virat Shejwalkar, Amir HoumansadrLanguage Model Safety EvaluationLLM Fine-Tuning

  2. On Optimizing Multimodal Jailbreaks for Spoken Language Models

    Mar 19, 2026Aravind Krishnan, Karolina Stańczak, Dietrich KlakowAdversarial AttacksLLM Jailbreak Attacks